{"slug": "learning-to-trust-claude-code", "title": "Learning to trust Claude Code", "summary": "Senior InfoWorld developer advocates trusting Claude Code as an agentic coding tool, arguing that developers who refuse to use AI agents due to mistrust are missing out on significant productivity gains. The author contends that coding agents, like human junior developers, require guidance, clear instructions, and iterative refinement to produce quality results. With proper guardrails and ongoing teaching, Claude Code can accelerate development by at least 10 times, making trust the critical factor separating slow, manual coders from those leveraging AI for rapid output.", "body_md": "I trust [Claude Code](https://www.infoworld.com/article/4136718/claude-code-is-blowing-me-away.html).\n\nBack in March, I wrote about why [I pity the developers](https://www.infoworld.com/article/4143101/pity-the-developers-who-resist-agentic-coding.html) who haven’t yet jumped on the agentic coding bandwagon. I also pity the developers just starting out, who will never quite understand the power that they now have at their fingertips.\n\nBut most of all, I really pity the developers who refuse to use [agentic development tools](https://www.infoworld.com/article/4052402/how-to-choose-the-right-ai-agent-development-tools.html) because they don’t trust AI agents.\n\nI understand that saying I trust Claude Code is a controversial statement. I know that the coding agent isn’t perfect, that it will make mistakes, that it will “hallucinate,” and that it will not always do what you want in the way you want it done.\n\nBut you can fix that.\n\nBut guess what? The same is true of every human developer on the planet. When you hire a new developer, especially a brand-new junior developer, they are going to make mistakes. They are going to misunderstand, and they are going to miss things that they shouldn’t.\n\nOf course, you’ll take the time to teach this person, show them the error of their ways, and help them grow. You learn what they know and don’t know, what they are good at, and what they are bad at.\n\nAnd admit it, even *you* sometimes take things in a bad direction and end up deleting half a day’s work, right?\n\nThe same is true for coding agents. Just like with a human developer, if you give your coding agent crappy instructions, if you don’t give it proper guidance, if you don’t take the time to point it in the right direction, you’ll get bad code. If you don’t keep an eye on things and continually nudge things in the right direction, you’ll end up in the wrong place. No surprise.\n\nAnd trust isn’t binary. Imagine if you hired a junior developer, gave them a two-sentence instruction, got back something that wasn’t quite right, and then fired them because of it. That would be silly, right? Well, that is what a lot of developers are doing with coding agents. Saying “I tried agentic coding, and it hallucinated something, so it is clearly worthless” isn’t any different.\n\nTrust takes time. You get out what you put in.\n\nMy practice has been to make sure those guardrails are in place, carefully track what Claude Code is up to, and continue to guide its responses and improve its instruction set. The more I do that, the better things go. I find that now I seldom have to steer things back onto the correct path.\n\nEven better, you can leverage solid guardrails and guidance from the very start. Tools like [gstack](https://github.com/garrytan/gstack) and [Superpowers](https://github.com/obra/superpowers) can turn Claude Code and a single developer into a whole company’s worth of coding intelligence.\n\nI’ve had great results. Claude Code gets my work done at least 10 times faster because I trust it. I’ve taken the time to teach it and provide it clear instructions, and — surprise! — it follows those instructions. And if it doesn’t, I can refine the guidelines and make things better.\n\nAnd just as it has always been among humans, trust is the key element that will separate those who plod along typing their own code, and those who move at the speed of light with a coding agent.", "url": "https://wpnews.pro/news/learning-to-trust-claude-code", "canonical_source": "https://www.infoworld.com/article/4172497/learning-to-trust-claude-code.html", "published_at": "2026-05-20 09:00:00+00:00", "updated_at": "2026-05-27 07:08:53.186221+00:00", "lang": "en", "topics": ["ai-agents", "ai-tools", "artificial-intelligence", "generative-ai"], "entities": ["Claude Code", "Infoworld"], "alternates": {"html": "https://wpnews.pro/news/learning-to-trust-claude-code", "markdown": "https://wpnews.pro/news/learning-to-trust-claude-code.md", "text": "https://wpnews.pro/news/learning-to-trust-claude-code.txt", "jsonld": "https://wpnews.pro/news/learning-to-trust-claude-code.jsonld"}}